A Novel Step towards Deep-Reinforcement Learning in a Cooperative Multi-agent System

9 Pages Posted: 1 Apr 2019

See all articles by Ginni Devi

Ginni Devi

Guru Nanak Dev University (GNDU) - Department of Computer Science and Engineering

Harjot Kaur

Guru Nanak Dev University (GNDU)

Date Written: 2018

Abstract

This study is an attempt to present a brief survey of several excellent works done by various authors in the field of multi-agent learning as well as multi-agent deep learning towards improving coordination and learning efficiency in the same. Based on the review of the existing work and research findings, we have proposed a framework to address coordination and learning issues in multi-agent learning. In this paper, we present a Networked–Deep Multi-agent Learning framework (N-DMAL), based upon implementation of deep reinforcement learning with social networks, that will result in improved learning efficiency of agents while interacting in a networked multi-agent system. The presented approach extends the traditional deep reinforcementlearning algorithm for agents’ interaction with other neighbouring agents when they coordinate in a cooperative manner.

Suggested Citation

Devi, Ginni and Kaur, Harjot, A Novel Step towards Deep-Reinforcement Learning in a Cooperative Multi-agent System (2018). International Journal of Information Systems & Management Science, Vol. 1, No. 1, 2018. Available at SSRN: https://ssrn.com/abstract=3363617

Ginni Devi (Contact Author)

Guru Nanak Dev University (GNDU) - Department of Computer Science and Engineering ( email )

India

Harjot Kaur

Guru Nanak Dev University (GNDU) ( email )

GT ROAD Amritsar
GT, ROAD AMRITSAR
Amritsar, Punjab 143005
India

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
44
Abstract Views
160
PlumX Metrics